WO2021129382A1

WO2021129382A1 - Video processing method and device

Info

Publication number: WO2021129382A1
Application number: PCT/CN2020/134645
Authority: WO
Inventors: 聂兰龙
Original assignee: 青岛千眼飞凤信息技术有限公司
Priority date: 2019-12-27
Filing date: 2020-12-08
Publication date: 2021-07-01
Also published as: CN113055586A

Abstract

Disclosed in the present application are a video processing method and device. The method comprises: receiving a trigger signal, wherein the trigger signal is used for triggering a camera device to perform photographing, the camera device comprising a driving device and a camera, the driving device being used for driving the camera in the camera device to move, and the camera being used for performing video capture during the movement; obtaining a video captured by the camera under the trigger of the trigger signal; extracting the identification information corresponding to a person in the video, and saving a corresponding relationship between the identification information and the video; obtaining the identification information of a video to be extracted, and searching the saved video for one or more videos corresponding to the identification information of the video to be extracted; and displaying the one or more videos to the user corresponding to the identification information of the video to be extracted. The present application solves the technical problem in the related art of low reliability of video processing methods.

Description

Video processing method and device

Technical field

This application relates to the technical field of video processing, and in particular to a video processing method and device.

Background technique

At present, the way to obtain video is mainly to use cameras, mobile phones, video cameras, and drones to obtain them independently. There is a lack of methods and means to provide high-quality video services.

High-quality video requires not only video capture equipment with good imaging effects, but also auxiliary shooting means. For example, the video captured using a traditional fixed camera has a rigid background and lacks dynamic effects, which makes it impossible to achieve an ideal presentation. For example, when shooting a movie, photographers usually need to set up rail cars and shooting cantilevers to achieve the ideal effect.

If the railcars and shooting cantilevers for professional movie shooting are transplanted into the scenic spot to provide tourists with video capture services, on the one hand, photographers need to be equipped to provide manual services, on the other hand, a large number of video clips will be generated through manual comparison and selection, and then The generated video is delivered to the user who was filmed. Manual comparison of video picking is inefficient. If the number of generated videos exceeds the workload of manual picking, the service effect will be affected.

In view of the low reliability of the video processing methods in the above-mentioned related technologies, no effective solution has been proposed at present.

Summary of the invention

The embodiments of the present application provide a video processing method and device to at least solve the technical problem of low reliability of video processing methods in the related art.

According to one aspect of the embodiments of the present application, there is provided a video processing method, including: receiving a trigger signal, wherein the trigger signal is used to trigger a camera device to shoot, and the camera device includes a driving device and a camera. The driving device is used for driving the camera in the camera device to move; the camera is used for video shooting during the movement; acquiring the video captured by the camera under the trigger of the trigger signal; extracting from the video The identity information corresponding to the person in the video is stored, and the corresponding relationship between the identity information and the video is stored.

Optionally, before receiving the trigger signal, the video processing method further includes: sensing that a person is present in the shooting range of the camera device through a sensor provided on the camera device; Induction, and send out the trigger signal.

Optionally, the sensor is at least one of the following: an infrared sensing unit, a radio frequency sensing unit, and a radar detection unit.

Optionally, before receiving the trigger signal, the video processing method further includes: receiving a user's operation of a switch in the camera device; and in response to the operation, sending the trigger signal.

Optionally, the switch is at least one of the following: a key switch unit, a touch switch unit, and a photoelectric switch unit.

Optionally, before receiving the trigger signal, the video processing method further includes: receiving a user's operation on a software interface; in response to the operation, sending the trigger signal to the camera device via a network.

Optionally, before receiving the user's operation on the software interface, the video processing method further includes: acquiring the identification information of the camera device by scanning a graphical code set on the camera device; and according to the identification information The operations that can be performed on the camera device are displayed on the software interface.

Optionally, after extracting the identification information corresponding to the person in the video from the video, and saving the corresponding relationship between the identification information and the video, the method further includes: acquiring Extract the identification information of the video, and search the saved videos for one or more videos corresponding to the identification information of the video to be extracted; display the one or more videos to the video to be extracted The user corresponding to the identification information.

Optionally, before receiving the user's operation on the software interface, the video processing method further includes: acquiring the geographic location information of the handheld device when the software interface displays the human handheld device; The geographic location information displays on the software interface the camera devices that can be controlled by the person within a predetermined range from the handheld device, and the operations that can be performed on the camera device.

Optionally, extracting the identification information corresponding to the person in the video from the video includes: extracting the sensed radio frequency identification information from the radio frequency signal; using the radio frequency identification information as the identity for identifying the person Identification information; extracting from the network trigger signal the identification information that identifies the person; acquiring the identification information of the video to be extracted includes: acquiring the radio frequency signal and extracting the sensed radio frequency identification information, and determining the radio frequency identification information as The identification information of the person; the identification information that identifies the person is extracted from the network trigger signal.

Optionally, extracting the identification information corresponding to the person in the video from the video includes: recognizing attachments on the person and/or biological characteristics of the person from the person; The feature information of the attachment and/or the feature information of the biological feature is used as the identification information for identifying the person; obtaining the identification information of the video to be extracted includes: obtaining the feature information and/or of the attachment of the person The identification information of the biological characteristics of the person, and the characteristic information of the attachment and/or the characteristic information corresponding to the biological characteristics are determined as the identification information of the person; wherein the attachment includes at least one of the following One: clothing, accessories, hand-held items; the biological characteristics include at least one of the following: facial characteristics, posture characteristics; the attachment is used to uniquely identify the person in a predetermined area.

Optionally, in a case where there are multiple persons in the video, extracting the identity information corresponding to the persons in the video from the video includes: identifying each of the multiple persons The attachments and/or biological characteristics of a person; the characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics are determined as the identification information of each of the multiple persons, and The corresponding relationship between the identification information of each of the multiple persons and the video is stored.

Optionally, storing the corresponding relationship between the identification information of each of the plurality of people and the video includes: determining that the identification information of each of the plurality of people is identified in the video Time node; use the time node as the time label of the identification information of each of the plurality of people; use the identification information of each of the plurality of people as the identity of each of the plurality of people The corresponding relationship between the time tag added by the identification information and the video is saved.

Optionally, the movement trajectory of the camera includes at least one of the following: a reciprocating movement trajectory between a predetermined starting point and a predetermined end point, a cyclic movement trajectory of a predetermined path, a movement trajectory designed based on a predetermined programming program, following the tracking movement of the target object Trajectory.

Optionally, the movement of the camera is at least one of the following: orbital movement and rotation movement.

Optionally, the driving mode of the driving device is at least one of the following: mechanical driving, electromagnetic driving, and pressure driving.

According to another aspect of the embodiments of the present application, there is also provided a video processing device, including: a first receiving unit, configured to receive a trigger signal, wherein the trigger signal is used to trigger a camera device to shoot, and the camera device It includes a driving device and a camera, the driving device is used to drive the camera in the camera device to move; the camera is used for video shooting during the movement; the first acquisition unit is used to acquire the camera in the The video taken under the trigger of the trigger signal; the extraction unit is used to extract the identity information corresponding to the person in the video from the video, and save the corresponding relationship between the identity information and the video .

Optionally, the video processing device further includes: a sensing unit, configured to sense that a person is present in the shooting range of the camera device through a sensor provided on the camera device before the trigger signal is received; A response unit is used for sending out the trigger signal in response to the sensing of the sensor.

Optionally, the video processing device further includes: a second receiving unit, configured to receive a user's operation of a switch in the camera device before receiving the trigger signal; and a second response unit, configured to respond to The operation sends the trigger signal.

Optionally, the video processing device further includes: a third receiving unit, configured to receive a user's operation on the software interface before receiving the trigger signal; a third response unit, configured to respond to the operation, The trigger signal is sent to the camera device via the network.

Optionally, the device further includes: a third obtaining unit, configured to obtain the identification information of the camera device by scanning a graphical code set on the camera device before receiving the user's operation on the software interface; The display unit is configured to display the operations that can be performed on the camera device on the software interface according to the identification information.

Optionally, the video processing apparatus further includes: a fourth acquiring unit, configured to acquire the handheld device when the software interface displays the human handheld device before receiving the user's operation on the software interface Geographic location information of the device; a display unit for displaying on the software interface the camera device that can be controlled by the person within a predetermined range of the handheld device according to the geographic location information, and the The operation performed by the camera.

Optionally, the device further includes: a second acquiring unit, configured to extract from the video the identity information corresponding to the person in the video, and to correlate the identity information with the video After the relationship is saved, the identification information of the video to be extracted is obtained, and one or more videos corresponding to the identification information of the video to be extracted are searched in the saved videos; the display unit is used to display the one or more Or multiple videos are displayed to the user corresponding to the identification information of the video to be extracted.

Optionally, the extraction unit is configured to identify the attachments on the person and/or the biological characteristics of the person from the person; and combine the characteristic information of the attachments and/or the biological characteristics of the person The characteristic information of the person is used as the identification information for identifying the person; the second acquiring unit is used to acquire the characteristic information of the person’s attachments and/or the identity information of the person’s biological characteristics, and the The characteristic information of the attachment and/or the characteristic information corresponding to the biological characteristic is determined to be the identification information of the person; wherein the attachment includes at least one of the following: clothing, accessories, and handheld objects; the biological characteristics include At least one of the following: facial features, posture features; the attachment is used to uniquely identify the person in a predetermined area.

Optionally, the extraction unit is further configured to extract the sensed radio frequency identification information from the radio frequency signal; use the radio frequency identification information as the identification information for identifying the person; extract the identification information from the network trigger signal. The identification information of the person; the second acquisition unit is further configured to acquire the radio frequency identification information sensed from the radio frequency signal, and determine the radio frequency identification information as the identification information of the person; from the network The trigger signal is extracted to obtain the identification information that identifies the person.

Optionally, when the number of people in the video is multiple, the extraction unit includes: a first identification module, configured to identify attachments and/or attachments on each person from the multiple people Or biological characteristics; the first storage module is used to determine the characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics as the identification information of each of the multiple persons, and The corresponding relationship between the identification information of each of the multiple persons and the video is stored.

Optionally, the first saving module includes: a first determining submodule, configured to determine the time node at which the identification information of each of the plurality of people is recognized in the video; and a second determining submodule , Used to use the time node as the time label of the identification information of each of the plurality of people; a save sub-module for storing the identification information of each of the plurality of people and the identification information of each of the plurality of people The corresponding relationship between the time tag added to each individual's identification information and the video is stored.

According to another aspect of the embodiments of the present application, a storage medium is also provided, the storage medium includes a stored program, wherein the program executes the video processing method described in any one of the foregoing.

According to another aspect of the embodiments of the present application, a processor is also provided, the processor is configured to run a program, wherein the video processing method described in any one of the above is executed when the program is running.

In the embodiments of the present application, the trigger signal is received, where the trigger signal is used to trigger the camera device to shoot. The camera device includes a driving device and a camera. The driving device is used to drive the camera in the camera to move; the camera is used to move the camera. Take video shooting during the process; obtain the video taken by the camera under the trigger signal; extract the identification information corresponding to the person in the video, and save the corresponding relationship between the identification information and the video, through the video in this application The processing method achieves the purpose of pre-saving the video containing the user and the identification information of the person identified from the video, and querying the user's video from the pre-stored video library according to the user's identification information, to achieve The technical effect of improving the reliability of the video processing method is improved, the user experience is improved, and the technical problem of low reliability of the video processing method in related technologies is solved.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application, and do not constitute an improper limitation of the application. In the attached picture:

Fig. 1 is a flowchart of a video processing method according to Embodiment 1 of the present application;

Fig. 2 is a schematic diagram of an application scenario of a photographing device according to the first embodiment of the present application;

Fig. 3 is a schematic diagram of a photographing device according to the first embodiment of the present application;

Fig. 4 is a schematic diagram 1 of an application scenario of a photographing device according to a second embodiment of the present application;

FIG. 5 is a second schematic diagram of an application scenario of the photographing device according to the second embodiment of the present application;

Fig. 6 is a schematic diagram of a photographing device according to a second embodiment of the present application;

Fig. 7 is a schematic diagram 1 of an application scenario of a photographing device according to a third embodiment of the present application;

FIG. 8 is a schematic diagram of a second application scenario of a photographing device according to the third embodiment of the present application;

Fig. 9 is a schematic diagram 1 of an application scenario of a photographing device according to a fourth embodiment of the present application;

10 is a schematic diagram of a second application scenario of a photographing device according to the fourth embodiment of the present application;

Fig. 11 is a schematic diagram of a photographing device according to a fourth embodiment of the present application;

FIG. 12 is a schematic diagram of an application scenario of a photographing device according to Embodiment 5 of the present application;

Fig. 13 is a schematic diagram of an application scenario of a photographing device according to the sixth embodiment of the present application;

Fig. 14 is a schematic diagram of a photographing device according to a sixth embodiment of the present application;

FIG. 15 is a schematic diagram of an application scenario of a photographing device according to Embodiment 7 of the present application;

Fig. 16 is a schematic diagram of a photographing device according to a seventh embodiment of the present application;

FIG. 17 is a schematic diagram of an application scenario of a photographing device according to Embodiment 8 of the present application;

Fig. 18 is a schematic diagram of a photographing device according to the eighth embodiment of the present application;

Fig. 19 is a schematic diagram of an application scenario of a photographing device according to the ninth embodiment of the present application;

Fig. 20 is a schematic diagram of a photographing device according to the ninth embodiment of the present application;

FIG. 21 is a schematic diagram of an application scenario of a photographing device according to the tenth embodiment of the present application;

Fig. 22 is a schematic diagram of a photographing device according to the tenth embodiment of the present application;

Fig. 23 is a schematic diagram of an application scenario of a photographing device according to the eleventh embodiment of the present application;

Fig. 24 is a schematic diagram of a photographing device according to the eleventh embodiment of the present application;

FIG. 25 is a schematic diagram of an application scenario of a photographing device according to the twelfth embodiment of the present application;

Fig. 26 is a schematic diagram of a photographing device according to the twelfth embodiment of the present application;

FIG. 27 is a schematic diagram of an application scenario of a photographing device according to the thirteenth embodiment of the present application;

Fig. 28 is a schematic diagram of a photographing device according to a thirteenth embodiment of the present application;

FIG. 29 is a schematic diagram of an application scenario of a photographing device according to the fourteenth embodiment of the present application;

Fig. 30 is a schematic diagram of a photographing device according to a fourteenth embodiment of the present application;

FIG. 31 is a schematic diagram of an application scenario of a photographing device according to the fifteenth embodiment of the present application;

Fig. 32 is a schematic diagram of a photographing device according to the fifteenth embodiment of the present application;

Fig. 33 is a schematic diagram of an application scenario of a photographing device according to the sixteenth embodiment of the present application;

Fig. 34 is a schematic diagram of a photographing device according to a sixteenth embodiment of the present application;

Fig. 35 is a schematic diagram 1 of an application scenario of a photographing device according to the seventeenth embodiment of the present application;

Fig. 36 is a schematic diagram 2 of an application scenario of a photographing device according to the seventeenth embodiment of the present application;

Fig. 37 is a schematic diagram of a photographing device according to a seventeenth embodiment of the present application; and,

Fig. 38 is a schematic diagram of a video processing device according to the eighteenth embodiment of the present application.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the application, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only These are a part of the embodiments of this application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

It should be noted that the terms "first" and "second" in the specification and claims of the application and the above-mentioned drawings are used to distinguish similar objects, and not necessarily used to describe a specific sequence or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those clearly listed. Those steps or units may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or equipment.

Example one

According to an embodiment of the present application, a method embodiment of a video processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, Although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

Fig. 1 is a flowchart of a video processing method according to an embodiment of the present application. As shown in Fig. 1, the video processing method includes the following steps:

Step S102: Receive a trigger signal, where the trigger signal is used to trigger the camera device to shoot, the camera device includes a drive device and a camera, the drive device is used to drive the camera in the camera device to move; the camera is used to perform video during the movement Shooting.

Optionally, the driving mode of the driving device is at least one of the following: mechanical driving, electromagnetic driving, and pressure driving. Among them, mechanical driving can be realized by rollers, ropes, conveyor belts, screw rods, etc.; electromagnetic driving can be realized by linear motors, magnetic levitation, etc.; pressure driving can be realized by fluid pressure such as hydraulic or pneumatic, for example, water energy, Wind energy, hydraulic pump function, air pump function, etc.

Optionally, when the driving device drives the camera in the camera device to move, it can be realized by installing a certain movement track, where the movement track of the camera can include at least one of the following: a reciprocating movement track between a predetermined starting point and a predetermined ending point, and a predetermined path The cyclic movement trajectory is based on the movement trajectory designed by a predetermined programming program and follows the tracking movement trajectory of the target object. That is, the movement trajectory can be a reciprocating movement between a predetermined start point and an end point, can be a cyclic movement according to a predetermined path, can be a movement that executes a predetermined programming program, can be a tracking movement following the target person, or a combination of the above movement modes; Mixed execution of movement modes, for example, a predetermined program is executed after the target person is tracked for a fixed period of time, and the target person is tracked for a fixed period of time after the execution of the predetermined program is completed.

Optionally, the movement mode of the camera is at least one of the following: orbital movement and rotational movement. Among them, the track can be a sliding track, a telescopic track, or a rope track; in a rotary movement, it can be rotated by a single joint, or can be rotated by multiple joints, and the rotating mechanism can be a rocker arm or a runner; in addition, , The movement method can also be a mixed movement of orbital movement and rotary movement.

In an optional embodiment, before receiving the trigger signal, the video processing method may further include: receiving a user's operation on the software interface; in response to the operation, sending a trigger signal to the camera device via the network.

In one aspect, before receiving the user's operation on the software interface, the video processing method may further include: acquiring the identification information of the camera device by scanning a graphical code set on the camera device; The operation performed by the device.

In another aspect, before receiving the user's operation on the software interface, the video processing method may further include: acquiring the geographic location information of the handheld device when the software interface displays the human handheld device; and displaying the geographic location information on the software interface based on the geographic location information Displays the camera devices that can be controlled by a person within a predetermined range from the handheld device, and the operations that can be performed on the camera device.

For example, the data information obtained by the network and sent by the portable terminal APP contains the user identification and confirms the use of the video capture device. The data information for confirming the use of the video capture device can be generated by the user entering the code of the video capture device in the APP application and confirming the use, it can be generated by the user using the APP application to scan the QR code of the video capture device, and it can be portable The terminal APP is generated based on the current location information of the portable terminal and the location information of the video capture device reaching a predetermined condition.

Step S104: Acquire a video captured by the camera under the trigger of the trigger signal.

In an optional embodiment, before receiving the trigger signal, the video processing method may further include: sensing that someone is present in the shooting range of the camera device through a sensor set on the camera device; Trigger signal.

Optionally, the aforementioned sensor is at least one of the following: an infrared sensing unit, a radio frequency sensing unit, and a radar detection unit.

That is, in this application, the sensor used to trigger the camera device may also be an infrared sensing unit that responds to infrared rays of the human body, a radio frequency sensing unit set to respond to radio frequency signals, or a radar responding to moving objects. Detection unit. Among them, in the embodiment of the present application, the radio frequency sensing unit may be a radio frequency identification RFID card.

In another optional embodiment, before receiving the trigger signal, the video processing method may further include: receiving a user's operation of a switch in the camera device; and in response to the operation, sending a trigger signal.

That is, in the present application, the sensor used to trigger the camera device may also be: a photoelectric switch unit that responds to the passage of a human body, a key switch unit that responds to pressing by the human body, or a touch switch unit that responds to human touch. .

In addition, the feature trigger unit that is used to trigger the start of the camera device can also be a feature trigger unit that responds to the person's gesture information, mouth shape information, and body shape information. It can be an instruction switch that responds to a network signal, for example, an instruction issued by a portable terminal APP through the network. Information, instruction information can be generated by the operation of the nearby video capture device selected in the APP, it can be entered in the APP of the code of the video capture device or the QR code of the device is scanned by the APP, and it can be that the APP obtains the positioning coordinates of the terminal in the mobile The video capture device is generated within the area set by the video capture device.

Step S106: Extract the identity information corresponding to the person in the video, and save the corresponding relationship between the identity information and the video.

Optionally, extracting the identification information corresponding to the person in the video may include: identifying attachments and/or biological characteristics of the person from the person; combining the characteristic information and/or biological characteristics of the attachment As the identification information used to identify the person.

In addition, in this embodiment of the application, the acquired video and the identification information identified from the video are saved correspondingly, and the support system can perform corresponding extraction operations on the video according to the corresponding saving, so that visitors can easily obtain video clips containing themselves. .

Furthermore, the acquired video and the identification information identified from the video are stored correspondingly. The video file may be mapped to the database and stored corresponding to the identification identification, or the summary information of the identification identification may be included in the video file.

It can be seen from the above that in the embodiments of the application, a trigger signal can be received, where the trigger signal is used to trigger the camera device to shoot. The camera device includes a driving device and a camera, and the driving device is used to drive the camera in the camera to move; For video shooting in the process of moving; to obtain the video captured by the camera under the trigger signal; to extract the identity information corresponding to the person in the video, and to save the corresponding relationship between the identity information and the video, realizing the advance The purpose of correspondingly saving the video containing the user and the identification information of the person identified from the video.

It is easy to notice that after the video is captured, the video is identified to obtain the identification information of the person in the video, and the video and the identified identification information are stored correspondingly, so that when the user requests to obtain his own video According to the user’s identity information, a video that is consistent with the user’s identity information can be called from the video library where the video is stored, so that the video containing the user can be pre-matched with the identity information of the person identified from the video. The purpose of saving and obtaining the user's video from the pre-stored video library according to the user's identity identification information is achieved, which achieves the technical effect of improving the reliability of the video processing method and improves the user experience.

Therefore, the video processing method in the present application solves the technical problem of low reliability of the video processing method in the related art.

In an optional embodiment, after extracting the identification information corresponding to the person in the video from the video, and saving the corresponding relationship between the identification information and the video, the video processing method further includes: obtaining the video to be extracted And search for one or more videos corresponding to the identification information of the video to be extracted in the saved videos; display one or more videos to the user corresponding to the identification information of the video to be extracted.

Optionally, acquiring the identification information of the video to be extracted may include: acquiring the characteristic information of the attachment of a person and/or the identification information of the biological characteristic of the person, and combining the characteristic information of the attachment and/or the characteristic information corresponding to the biological characteristic Identification information determined as a person; wherein the attachment includes at least one of the following: clothing, accessories, and hand-held objects; the biological characteristics include at least one of the following: facial features, posture characteristics; the attachment is used to uniquely identify a person in a predetermined area.

In addition, when the number of people in the video is multiple, extracting the identification information corresponding to the people in the video may include: identifying attachments and/or biological characteristics of each person from multiple people; The characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics are determined as the identification information of each of the multiple people, and the corresponding relationship between the identification information of each of the multiple people and the video is determined save.

In an optional embodiment, storing the corresponding relationship between the identification information of each of the multiple people and the video includes: determining the time node at which the identification information of each of the multiple people is recognized in the video ; The time node is used as the time label of the identification information of each of the multiple people; the identification information of each of the multiple people and the time label added for the identification information of each of the multiple people are corresponding to the video The relationship is saved.

In another optional embodiment, extracting the identification information corresponding to the person in the video from the video includes: extracting the sensed radio frequency identification information from the radio frequency signal; using the radio frequency identification information as the identification information for the person Identification information; the identification information that identifies the person is extracted from the network trigger signal; the identification information of the video to be extracted includes: extracting the sensed radio frequency identification information from the radio frequency signal, and determining the radio frequency identification information as the identity of the person Information; the identification information that identifies the person is extracted from the network trigger signal.

For example, extracting the identification information corresponding to the person in the video from the video can be implemented by an identification unit, which can be a radio frequency identification unit carried by a person, such as an RFID card.

For another example, extracting the identification information corresponding to the person in the video from the video can be realized by the identification unit, which can be the identification information obtained by the network, for example, the network obtained by the portable terminal APP issued by the user contains the user Identification and confirmation of the use of the video capture device data information. The data information for confirming the use of the video capture device can be generated by the user entering the code of the video capture device in the APP application and confirming the use, it can be generated by the user using the APP application to scan the QR code of the video capture device, and it can be portable The terminal APP is generated based on the current location information of the portable terminal and the location information of the video capture device reaching a predetermined condition.

Figure 2 is a schematic diagram of the application scenario of the camera according to the first embodiment of the application, and Figure 3 is a schematic diagram of the camera according to the first embodiment of the application, as shown in Figures 2 and 3, in this embodiment, a convex track is used to reciprocate Movement, the driving method is roller drive, and the movement track is straight back and forth. This implementation can be applied to indoor exhibition halls. The trigger method adopted is the human body infrared sensor switch, and the track of the camera device (including the track and the video capture car) is convex. track.

In this embodiment, there are proximity switches on both sides of the video capture sports car, and there are limit iron blocks at both ends of the track. When the sports car moves to the limit iron block, the proximity switch senses the limit iron block and stops the movement in the current direction. Start moving in the opposite direction. Move to the limit iron block at the other end, in response to the proximity switch sensing signal, stop the movement in the current direction, and start the movement in the opposite direction. The video captures the uninterrupted linear motion of the sports car back and forth between the two limit iron blocks. The video capture sports car responds to the signal sensed by the infrared sensor switch of the human body, and starts the uninterrupted round-trip linear motion when the human body infrared is sensed, and executes the operation of acquiring the video; if the human body infrared is not sensed, it stops The uninterrupted reciprocating linear movement.

The video capture vehicle (or called a sports car) is equipped with running wheels and provides wireless connection. Proximity switches are arranged at both ends of the sports car, and carbon brushes are arranged at the front and rear of the sports car; the two ends of the track are arranged with limit iron posts that can be sensed by the proximity switch, and conductive cables are arranged on both sides of the angle steel track to provide electricity for the sports car.

In the embodiment, the video segment can be generated in the following way: extract the video segment from the continuously captured video stream, take the time point when the RFID radio frequency signal is sensed as the first frame of the video segment, and take the time point when the RFID radio frequency signal disappears as sensed The end frame of the video clip. The sensed RFID radio frequency identification is saved in the extracted video file abstract. The RFID radio frequency card triggers the sports car to start linear reciprocating movement through the human body infrared sensor switch and obtain the video operation, which can avoid the device from performing invalid operations, and can automatically capture the tourists' mobile video at any time. Behind the booth of the exhibition hall, the video captures the sports car reciprocating on the corner track, continuously shooting the same frame video of the visitors and the exhibits.

Example two

4 is a schematic diagram of the first application scenario of a photographing device according to the second embodiment of the application, FIG. 5 is a schematic diagram two of the application scenario of the photographing device according to the second embodiment of the present application, and FIG. 6 is a schematic diagram of the photographing device according to the second embodiment of the present application, as shown in FIG. 4. As shown in Figures 5 and 6, in this embodiment, a concave circular track is used, its driving mode is a timing belt wheel, and its motion track is a curve cycle-character tracking. This implementation can be applied to a slide. The trigger mode is facial recognition, and the movement form is a concave track.

In this embodiment, after triggering, a video capture sports car is started, and the target person is tracked from the starting point to the end point, and after reaching the end point, it queues with other video capture sports cars to wait for the servo. The video capture car (or called a sports car) uses a DC miniature gear reducer motor, a synchronous wheel, and a toothed synchronous belt. The video capture car can be connected wirelessly.

In this embodiment, the first frame of the video clip starts when the video capture sports car starts to move, and the video capture sports car moves to the bottom end of the track to generate the end frame. The video clip does not contain the capture information from the top of the track to the end. The file name of the generated video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier. In this embodiment, facial feature recognition is used. By recognizing tourists with registered facial features, the camera can be triggered to start the mobile vehicle to perform the mobile acquisition video operation, which can autonomously track and shoot, and achieve a presentation effect that cannot be achieved by conventional shooting methods.

When the target person descends from the slide, the first video captures the sports car to automatically track and shoot. The second video captures the sports car in a ready position. On the other side of the track, there are four video-capture sports cars waiting for the servo. The video captures the sports car in a concave track. The sports car is powered by two electric carbon brushes. The sports car is equipped with a DC miniature gear reducer motor. The synchronous wheel on the output shaft of the reducer meshes with the toothed synchronous belt pasted in the track. Two conductive cables are pasted on one side wall of the track to provide electricity for the video capture sports car through the carbon brush of the sports car.

Example three

FIG. 7 is a schematic diagram of the first application scenario of the photographing device according to the third embodiment of the present application, and FIG. 8 is a schematic diagram of the second application scenario of the photographing device according to the third embodiment of the present application, as shown in FIG. 7 and FIG. The video captures the sports car on the ceiling of the T-shaped show stage performance hall, which moves circularly along the curve of the snake-shaped slit track. In this embodiment, the slit-shaped snake track is adopted. The driving mode is a roller, and the movement track is a curve loop. The example can be applied to the T-shaped runway. In this embodiment, a master control switch is used for triggering, and the track can be a ceiling cracked track.

In this embodiment, after the main control switch is closed, the video capture sports car cyclically moves along the track curve; after the main control switch is opened, the video capture sports car stops moving.

The recognition method in this embodiment is facial feature recognition. The video segment is extracted from the continuously captured video stream, and a fixed time point before the time point when the facial feature is recognized is the first frame of the video segment, and the first frame time point is The fixed time point afterwards is the end frame. The ingested video fragment is analyzed for the degree of facial expression richness change, and the video fragment that meets the determination of the degree of facial expression richness change is stored corresponding to the facial feature recognition identifier. The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier. After the mobile video acquisition device is turned on, the video is captured continuously, and fixed-length videos before and after the time point when the facial features of the person are recognized are extracted from the continuous video, and the wonderful moments in the video with rich changes in the expression of the person are recorded.

Example four

FIG. 9 is a schematic diagram of the first application scenario of a photographing device according to the fourth embodiment of the application, FIG. 10 is a schematic diagram of the second application scenario of the photographing device according to the fourth embodiment of the present application, and FIG. 11 is a schematic diagram of the photographing device according to the fourth embodiment of the present application, as shown in FIG. 9. As shown in Figures 10 and 11, in this embodiment, the video capture device is located at the lowest end of the hexagonal column in the non-working state, the target person stands on the lifting platform, and the video capture device is dragged to the corner of the hexagonal column by a drawstring. Top. The movable frame is arranged on the periphery of the hexagonal column to drive the video capture device to move. This embodiment uses a rod-shaped octahedral column, a pull rope, and a way of rotating up and down. This embodiment can be applied to urban parks. The trigger mode of this embodiment is gravity downward pressure, the movement mode is a vertical pole track, and the driving mode is Activities frame.

In this embodiment, the pull rope between the lifting platform and the video capture movable frame drives the video capture movable frame to rotate and move. For example, if the lifting platform is pressed and dropped by gravity, the video capture movable frame performs rotation and upward movement, for example, the lifting platform Cancel the gravity downward pressure rise, then the video capture activity frame will perform a rotating downward movement.

In this embodiment, an external network instruction identifier can be used, for example, an APP registered user scans the code of the mobile video acquisition device or enters the device number (APP registration identifier).

The way of generating the video can be as follows: a proximity switch is provided on the pole, and the movable frame is in the lowest position in response to the video capture. The video capture frame leaves the lowest position, and responds to the signal from the proximity switch to start capturing video and generates the first frame of the video clip; the video capture frame returns to the lowest position and responds to the signal from the proximity switch to generate the end frame of the video clip, and Stop video capture.

Match the captured video clip with the network trigger mark, and save the video clip matching the network trigger mark corresponding to the mark. The received network trigger identifier is stored in the generated video file summary.

Use the portable terminal APP to scan the code to confirm the mobile video acquisition device, and use this device to perform mobile acquisition video operations. The shooting angle of view can be gradually increased from the horizontal angle of view containing the user to the high-altitude angle of view of the panoramic view of the scenic area, which cannot be achieved by conventional shooting methods. The rendering effect.

Example five

FIG. 12 is a schematic diagram of an application scenario of a photographing device according to Embodiment 5 of the present application. As shown in FIG. 12, this embodiment can be applied to a climbing ladder, and a rope track is provided on one side of the climbing ladder. The rope puller drags the video capture device to slide along the rope track. This embodiment can be referred to as a rope type. In this embodiment, a rope puller is used as a drive, a fixed trajectory is adopted, the trigger mode is an RFID radio frequency card, and the movement form is a rope track.

Both ends of the rope track and the mobile video acquisition device are equipped with RFID readers, which can read passive RFID radio frequency cards that meet the ISO/IEC18000-6 standard 860-960MHz air interface parameters within 10m.

The video capture unit is connected to the pull rope, and a rope puller is arranged at the top of the rope track.

In response to the radio frequency signal identification received by the RFID reader, the rope puller drags the mobile video acquisition device to perform reciprocating movement at both ends of the rope track, and pulls it for a fixed period of time in response to the time point when the RFID reader cannot receive the radio frequency signal. The rope device stops dragging the mobile video capture device.

In response to the radio frequency information identification received by the RFID reader set on the mobile video capture device, the rope puller reduces the drag speed; in response to the RFID reader set on the mobile video capture device cannot receive Radio frequency information identification, the rope puller resumes towing speed.

In this embodiment, an RFID radio frequency card is used as identity recognition. In response to receiving the RFID radio frequency information, video capture is performed. In response to not receiving the RFID radio frequency information, the video capture is executed after a fixed period of time and the video file is generated. The file name of the generated video file is mapped in a database, and the video file in the database corresponds to a plurality of RFID radio frequency information containing time tags.

The RFID radio frequency information including the time tag records the sensed RFID radio frequency information and the corresponding time point information, the time point information is the time point information when the radio frequency information is received, and the time point information is not received Time point information of the radio frequency information.

Through the ultra-high frequency band RFID card, the mobile video capture device can capture the video of users within 10m, and reduce the speed of movement when moving to the vicinity of the user to enhance the presentation effect of shooting for the user.

Example Six

FIG. 13 is a schematic diagram of an application scenario of a photographing device according to Embodiment 6 of the present application, and FIG. 14 is a schematic diagram of a photographing device according to Embodiment 6 of the present application. As shown in FIG. 13 and FIG. 14, this embodiment can be applied to trampoline sports. In this embodiment, the video capture device tracks the target person on the trampoline moving up and down to shoot. Linear motor induction coils are arranged on both sides of the video capture device, which respectively penetrate two tubular magnetic shafts.

This embodiment can be called a linear motor type, and its driving mode is a tubular high-speed servo linear motor, and its trajectory is linear reciprocating. The movement form can be a tubular track. The tubular high-speed servo linear motor responds to the video image portrait analysis of the background server. After the character enters the target area, the magnetic axis linear motor moves to the position corresponding to the height of the character's head, and responds to the video image portrait analysis Track the height of the person's head to track the movement.

The trigger method used may be an external network instruction method. For example, the portable terminal APP detects that the positioning coordinates are located in a predetermined area and sends a trigger instruction to the mobile video acquisition device in the predetermined area. If the positioning coordinates of the portable terminal are located in the setting area of the mobile video acquisition device, the APP registration identifier can be acquired, which is used as the identification identifier. Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip.

Slow motion effect processing is performed on the extracted video segment, and the extracted video segment is saved corresponding to the facial feature recognition identifier. The file name of the generated video file is mapped in the database, and the video file in the database corresponds to the network trigger identifier.

The high-speed servo linear motor drives the high-speed camera to track the movement in response to the moving state of the person, and achieve the effect that cannot be presented in conventional shooting through the slow-motion effect.

In the following embodiments, the seventh to tenth embodiments and the thirteenth to seventeenth all use facial recognition as the identity recognition method, and the eleventh embodiment uses an RFID radio frequency card as the identity recognition method, and the twelfth embodiment The image feature recognition of the name badge is used as the identification method.

Example Seven

15 is a schematic diagram of the application scenario of the photographing device according to the seventh embodiment of the present application. FIG. 16 is a schematic diagram of the photographing device according to the seventh embodiment of the present application. As shown in FIG. 15 and FIG. 16, this embodiment can be called a magnetic levitation track, which can be applied In the Science and Technology Museum, in this embodiment, the target person touches and clicks on the touch screen to trigger the magnetic levitation video capture of the sports car to move back and forth in a straight line. The lower part of the magnetic levitation video capture sports car is provided with two skateboards, and the skateboard has a built-in magnet to make the video capture sports car levitate on the track. In this embodiment, the driving mode is a magnet and an induction coil, the trajectory is a straight back and forth, the trigger mode is a touch switch, and the movement mode is a magnetic levitation track. The magnetic levitation video capture sports car is equipped with magnets on both sides of the skateboard, and the magnets with the same magnetism as the sports car magnet are arranged on both sides of the track, and the magnetic levitation video captures the sports car floating above the track. A horizontal magnetic column is arranged in the middle of the magnetic levitation video capture sports car, and a horizontal coil is arranged in the middle of the track to attract the horizontal magnetic column. The horizontal coil in the middle of the track drives the horizontal magnetic column of the sports car to move.

The magnetic levitation video captures the sports car to perform reciprocating movement on the track according to a predetermined programmed trajectory. In response to the touch switch signal, a fixed number of linear reciprocating movements are initiated, and the operation of acquiring the video is performed. Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip.

The extracted video clips are saved corresponding to the facial feature recognition identifiers. The file name of the generated video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

The human body infrared sensor switch triggers the sports car to start linear reciprocating movement and obtain video operations, which can prevent the device from performing invalid operations and automatically capture tourists on mobile at any time.

Example eight

FIG. 17 is a schematic diagram of an application scenario of a photographing device according to Embodiment 8 of the present application, and FIG. 18 is a schematic diagram of a photographing device according to Embodiment 8 of the present application. As shown in FIG. 17 and FIG. This embodiment can be applied to extreme sports. In extreme sports venues, the lifting screw sliding table tracks the target person for moving and shooting. The servo motor drives the lead screw to rotate and drives the video capture device to move up and down. The driving mode of this embodiment is a lead screw and a sliding table, its trajectory is a tracking trajectory, its trigger mode is a portrait analysis, and its movement form is a linear track.

The lead screw sliding table responds to the video image portrait analysis of the back-end server, the sliding table moves to the position corresponding to the height of the person's head after the person enters the target area, and tracks the height of the person's head in response to the video image portrait analysis. Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip. The extracted video clips are saved corresponding to the facial feature recognition identifiers. The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier. By tracking the movement in response to the moving state of the character, the movement process is recorded, and the effect that cannot be presented by conventional shooting is realized.

Example 9

FIG. 19 is a schematic diagram of an application scenario of a photographing device according to Embodiment 9 of the present application, and FIG. 20 is a schematic diagram of a photographing device according to Embodiment 9 of the present application. As shown in FIG. 19 and FIG. 20, this embodiment can be referred to as the implementation of the hanging wheel mode. For example, this embodiment can be applied to a passageway in a scenic spot, where a mobile video capture device installed on the upper part of a street light pole moves up and down to shoot a target person. The upper part of the street light pole is equipped with a spherical radar sensor device, a rope puller, and a hanging wheel video capture device. The driving mode of this embodiment is a rope puller, the trajectory is up and down, and the trigger mode is that the radar sensor switch moves in the form of a sling reciprocation. In this embodiment, after the radar sensor switch detects a moving object, the video capture device moves up and down along the sling Moving; when the radar sensor switch detects no moving objects, the video capture device stops moving.

A video clip is extracted from a continuously captured video stream, and a fixed time point before the time point when the facial feature is recognized is the first frame of the video clip, and a fixed time point after the first frame time point is the end frame. Extract video clips for different facial feature recognition subjects, and save the extracted video clips corresponding to the facial feature recognition identifiers. The file summary of the generated video file corresponds to multiple facial feature recognition identifiers containing time stamps.

The facial feature recognition identifier containing the time tag records the recognized facial features and the corresponding time point information. The time point information is the time point information at which the facial feature is recognized, and the time point information is that the face cannot be recognized The time point information of the feature. Through this embodiment, the autonomous shooting angle of view can be gradually increased from the horizontal angle of view that includes tourists to the high-altitude angle of view that overlooks the entire scenery of the scenic area, and achieves a presentation effect that cannot be achieved by conventional shooting methods.

Example ten

FIG. 21 is a schematic diagram of an application scenario of a photographing device according to Embodiment 10 of the present application. FIG. 22 is a schematic diagram of a photographing device according to Embodiment 10 of the present application. As shown in FIG. 21 and FIG. 22, this embodiment can be called a conveyor belt type. It is applied to the hot spots of crowded scenic spots. In the hot spots of scenic spots, the video capture device on the conveyor belt continuously moves the people in the shooting area. The conveyor belt is driven by a geared motor, which drives multiple video capture devices to shoot.

The driving mode of this embodiment is a reduction motor and a runner, the trajectory is a belt loop, the trigger mode is a master control switch, and the movement mode is a conveyor belt loop. After the main control switch is closed, the video capture device moves up and down along the sling; after the main control switch is opened, the video capture device stops moving.

A video clip is extracted from a continuously captured video stream, and a fixed time point before the time point when the facial feature is recognized is the first frame of the video clip, and a fixed time point after the first frame time point is the end frame. Extract video clips for different facial feature recognition subjects, and save the extracted video clips corresponding to the facial feature recognition identifiers.

The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

Install multiple mobile capture devices on the conveyor belt, which can efficiently capture video movement in crowded areas and realize multiple angles of people.

Example 11

FIG. 23 is a schematic diagram of an application scenario of a photographing device according to Embodiment 11 of the present application, and FIG. 24 is a schematic diagram of a photographing device according to Embodiment 11 of the present application. As shown in FIG. 23 and FIG. 24, this embodiment may be called a scissor lift type This embodiment can be applied to temporary scenic spots. In this embodiment, the video capture device is temporarily placed at the temporary scenic spot to shoot the target person from the bottom up. The hydraulic station drives the oil cylinder to drive the lifting device of the scissor fork structure to reciprocate up and down.

The driving mode of this embodiment is oil pressure, the trajectory is a programmed trajectory, the trigger mode is a master control switch, and the movement form is a retractable lifting structure, such as a scissor fork lifting. After the main control switch is closed, the video capture device moves up and down along the sling; after the main control switch is opened, the video capture device stops moving.

Extract video fragments from the continuously captured video stream, and use the RFID reader on the mobile video acquisition device to receive the radio frequency information identification time point before the fixed time point is the first frame of the video fragment, and use it on the mobile video acquisition device The fixed long time point after the RFID reader fails to receive the radio frequency information identification is the end frame of the video clip.

The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the RFID radio frequency information identification.

Through the ultra-high frequency band RFID card, the mobile video capture device can capture the video of users within 10m, and can complete the autonomous shooting angle from the horizontal angle of the tourist to the high-altitude angle of view of the entire scenic spot, enhancing the user-oriented shooting Present the effect. The mobile video acquisition device can be dragged to a temporary location at any time to perform the task of video capture according to the temporary needs of the scenic spot.

Example 12

FIG. 25 is a schematic diagram of an application scenario of a photographing device according to the twelfth embodiment of the present application, and FIG. 26 is a schematic diagram of a photographing device according to the twelfth embodiment of the present application. As shown in FIG. 25 and FIG. 26, this embodiment may be called a multi-section rod This embodiment can be applied to the entrance of a scenic spot. In this embodiment, the target person passes through the photoelectric switch sensing area, and in response to the photoelectric switch sensing signal, the cylinder performs an upward movement to drive the video capture device to shoot the target person. A travel switch is arranged at the top of the vertical pole, and the travel switch signal triggers the cylinder to perform a downward movement. This embodiment is a power air system composed of an air compressor, an oil-water separator, an electromagnetic reversing valve, and an air cylinder, which drives the video capture device to move up and down.

In this embodiment, the driving mode is an air cylinder, the trajectory is reciprocating, the trigger mode is a photoelectric switch, and the movement mode is a multi-section air cylinder. The mobile video acquisition device is set on the top of the multi-section cylinder. The pneumatic pipeline electromagnetic reversing valve controls the expansion and contraction of the multi-section cylinder. The electromagnetic reversing valve responds to the off signal of the optoelectronic switch to control the elasticity of the cylinder; the electromagnetic reversing valve In response to the closing signal of the limit switch, the cylinder is controlled to contract.

The mobile video acquisition device starts to capture the first frame of the video clip at the time when the through-beam photoelectric switch is turned off, and the time point after the time when the travel switch is closed is the end of the captured video clip. frame. The generated video clips are saved correspondingly to the feature identification marks of the badge. The image feature identification of the badge identified in the file summary of the generated video file.

By the tourists entering the entrance of the scenic spot, the multi-section cylinder is triggered to stretch out and start to execute the mobile acquisition video operation, and the autonomous shooting angle can be gradually increased from the horizontal angle of view containing tourists to the high-altitude angle of view of the panoramic view of the scenic area, realizing a presentation that cannot be achieved by conventional shooting methods effect.

Embodiment 13

FIG. 27 is a schematic diagram of an application scenario of a photographing device according to Embodiment 13 of the present application. FIG. 28 is a schematic diagram of a photographing device according to Embodiment 13 of the present application. As shown in FIG. 27 and FIG. 28, this embodiment may be called a two-way slide . This embodiment can be applied to an art gallery. When a target person passes through the art gallery, the mobile video acquisition device is driven by a two-way slide to track and shoot. A power supply cable and a rack are arranged on the first rail, which respectively mesh with the power-taking carbon brush and the output shaft gear of the first servo motor. The second track is arranged on the first sliding table, and the second track is arranged with a rack gear which meshes with the gear of the output shaft of the second servo motor. A connection line is provided between the first servo motor and the second servo motor, and is wrapped in the protective drag chain. The video capture device is arranged on the second sliding table.

The driving mode of this embodiment is a synchronous belt and a synchronous wheel, the trajectory is a tracking-programming trajectory, the trigger mode is a portrait analysis, and the movement form is a sliding rail. In this embodiment, the mobile video acquisition device is configured to program multiple sets of predetermined trajectories corresponding to the multi-angle shooting of the artwork.

The mobile video acquisition device responds to the portrait analysis of the video image of the back-end server, tracks and acquires the activity video of the person for a fixed period of time and executes the predetermined trajectory programming of the artwork that the person looks at or the artwork near the person, and continues to respond to the background after the execution of the predetermined trajectory programming is completed. The server's video image portrait analysis tracks people for a fixed period of time.

Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip. Extract video segments from different facial feature recognition subjects, and save the extracted video segments corresponding to the facial feature recognition identifiers. The file name of the generated video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

By tracking the movement of the target person and switching between the predetermined programmed trajectory, it is possible to achieve the effect of natural switching and alternate presentation of the subject between the person and the shooting scene.

Example Fourteen

FIG. 29 is a schematic diagram of an application scenario of a photographing device according to Embodiment 14 of the present application. FIG. 30 is a schematic diagram of a photographing device according to Embodiment 14 of the present application. As shown in FIG. 29 and FIG. This embodiment can be applied to a water park. The video capture device is set at the bottom end of the water storage bucket. If the water level in the water storage bucket reaches a predetermined water level, the video capture device will move upward as the center of gravity of the water storage bucket shifts; After the water in the bucket is emptied, the video capture device moves down with the return of the water bucket.

In this embodiment, the shooting state may include: a bucket, a rotating shaft, a water valve, a video capture device, and a counterweight. In this embodiment, the driving mode is water energy, the trajectory is water pressure back and forth, the trigger mode is water flow, and the movement mode is When a single rotating shaft rotates and there is water flow, the water storage bucket performs repeated swings relative to the rotating shaft, and the mobile video acquisition device at one end of the water storage bucket moves up and down in an arc with the rotating shaft as the center.

Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip. The extracted video clips are saved corresponding to the facial feature recognition identifiers. The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

Through this embodiment, the autonomous shooting angle of view can be gradually increased from the horizontal angle of view containing tourists to the high-altitude angle of view of the overview of the panoramic view area, realizing a presentation effect that cannot be achieved by conventional shooting methods.

Example 15

FIG. 31 is a schematic diagram of an application scenario of a photographing device according to Embodiment 15 of the present application. FIG. 32 is a schematic diagram of a photographing device according to Embodiment 15 of the present application. As shown in FIG. 31 and FIG. 32, this embodiment may be called a turntable type. This embodiment can be applied to a water park, where multiple video capture devices are arranged on a rotating water wheel, and multiple video capture devices perform continuous shooting at the same time. The photographing device in this embodiment may include: a waterwheel, a water valve, a video capture device, and a counterweight.

The driving mode of this embodiment is water energy, the trajectory is cyclic, the trigger mode is water flow, and the movement mode is single-rotation shaft rotation. In the case of water flow, the water storage bucket phase drives the runner to perform circular movement, and a plurality of mobile video acquisition devices arranged on the runner move circularly with respect to the rotating shaft.

Extract video clips from the continuously captured video stream, take the time point in the video image analysis that the person enters the target area after a fixed period of time as the first frame of the video clip, and take the time point in the video image analysis that the person leaves the target area before the time point The fixed time point is the end frame of the video clip. Extract video segments from different facial feature recognition subjects, and save the extracted video segments corresponding to the facial feature recognition identifiers. The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

Through this embodiment, the autonomous shooting angle of view can be gradually increased from the horizontal angle of view that includes tourists to the high-altitude angle of view that overlooks the entire scenery of the scenic area, and achieves a presentation effect that cannot be achieved by conventional shooting methods.

Example Sixteen

FIG. 33 is a schematic diagram of an application scenario of a photographing device according to the sixteenth embodiment of the present application, and FIG. 34 is a schematic diagram of a photographing device according to the sixteenth embodiment of the present application. As shown in FIG. 33 and FIG. 34, this embodiment may be referred to as a multi-axis pan The arm, this embodiment can be used for a spiral ladder, and the video capture device tracks the movement of the target person walking on the spiral ladder. The first stepping motor drives the first rocker arm to rotate, and the second stepping motor drives the second rocker arm to rotate. The second rocker arm rotating shaft is arranged on the first rocker arm.

In this embodiment, the driving mode is a stepping motor, the trajectory is a tracking trajectory, the trigger mode is a portrait analysis, and the movement mode is an early joint rotation. The turntable and the rocker arm respond to the portrait analysis of the video image of the background server, and the rocker turntable makes the video acquisition device track the movement of the head position of the person after the person enters the target area.

In response to the portrait analysis of the video image by the back-end server, the mobile video acquisition device extracts a fixed time point before the time point when the portrait appears in the predetermined area as the first frame of the video clip, and the time point when the portrait leaves the predetermined area as the video clip End frame. Save the generated video clip corresponding to the facial feature recognition identifier. The file name of the generated video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

Through the free rotation of multiple joints, the mobile video acquisition device of this embodiment tracks the target person for shooting, and achieves a presentation effect that cannot be achieved by conventional shooting means.

Example Seventeen

35 is a schematic diagram of the first application scenario of a photographing device according to the seventeenth embodiment of the application, FIG. 36 is a schematic diagram of the second application scenario of the photographing device according to the seventeenth embodiment of the present application, and FIG. 37 is a schematic diagram of the photographing device according to the seventeenth embodiment of the present application , As shown in Figure 35, Figure 36 and Figure 37, this embodiment can be called a sliding table rocker combination. This embodiment can be applied to the welcome lane of a scenic spot. A welcome device is installed on the welcome lane of the scenic spot. Waving the flagpole, the welcoming device is also equipped with a video capture device. In the welcome device, the first cylinder controls the telescopic movement of the scissor and fork mechanism on the sliding table, and the second cylinder controls the rocker arm to swing up and down. The photographing device in this embodiment may include: an air pump, an oil-water separator, a first cylinder, a first electromagnetic directional valve, a second electromagnetic directional valve, a second cylinder, a third electromagnetic directional valve, and a fourth electromagnetic directional valve .

The driving mode of this embodiment is an air cylinder, the trajectory is a random and disordered trajectory, the trigger mode is a master control switch, and the movement form is a linear reciprocating and single-joint rotation of the sliding table. The slide table is set to the expansion control of the first cylinder, and the rocker arm is set to the expansion control of the second cylinder. The first solenoid reversing valve controls the extension of the first cylinder, the second solenoid reversing valve controls the contraction of the first cylinder, the first solenoid reversing valve and the second solenoid reversing valve are set within 5-20 seconds Randomly select a certain time as the two reversing valve commands to alternately execute and control the operating time of the first cylinder. For example, randomly select 8 seconds as the first time sequence, the first electromagnetic reversing valve ventilates the cylinder, and the second electromagnetic reversing valve exhausts outwards, so that the sliding table moves to one end; after 8 seconds, the second time sequence is entered; random selection 17 seconds is the second time sequence. The first solenoid reversing valve and the second solenoid reversing valve execute commands interchange, the first solenoid reversing valve exhausts outwards, and the second solenoid reversing valve ventilates the first cylinder to achieve sliding The stage moves in the opposite direction, and the third sequence is performed after 17 seconds.

The third solenoid reversing valve controls the extension of the second cylinder, the fourth solenoid reversing valve controls the contraction of the second cylinder, the third solenoid reversing valve and the fourth solenoid reversing valve are set within 3-12 seconds Randomly select a certain time as the two reversing valve commands to alternately execute and control the operating time of the second cylinder. For example, randomly select 5 seconds as the first time sequence, the third electromagnetic reversing valve ventilates the cylinder, and the fourth electromagnetic reversing valve exhausts outwards to realize the upward movement of the rocker arm; after 5 seconds, it enters the second time charge; random selection 9 seconds is the second time sequence. The third solenoid reversing valve and the fourth solenoid reversing valve execute commands interchange, the third solenoid reversing valve exhausts outward, and the fourth solenoid reversing valve ventilates the second cylinder to achieve shaking. The arm moves down, and the third sequence is performed after 9 seconds.

After the main control switch is closed, the video capture device follows the sliding table and rocker arm to move randomly; after the main control switch is turned off, the video capture device stops moving.

Extract a video segment from a continuously captured video stream, and use a fixed time point before the facial feature recognition time point as the first frame of the video segment, and a fixed time point after the first frame time point as the end frame. Extract video clips for different facial feature recognition subjects, and save the extracted video clips corresponding to the facial feature recognition identifiers. The file name of the extracted video file is mapped in the database, and the video file in the database corresponds to the facial feature recognition identifier.

Embodiment 18

According to another aspect of the embodiments of the present application, there is also provided a device for executing the video processing method of one of the foregoing embodiments. FIG. 38 is a schematic diagram of the video processing device according to the embodiment of the present application, as shown in FIG. 38 , The video processing device includes: a first receiving unit 3801, a first acquiring unit 3803, and an extracting unit 3805. The video processing device will be described in detail below.

The first receiving unit 3801 is used to receive a trigger signal, where the trigger signal is used to trigger the camera device to shoot, the camera device includes a driving device and a camera, the driving device is used to drive the camera in the camera to move; the camera is used to move Video shooting during the process.

The first acquisition unit 3803 is configured to acquire a video captured by the camera under the trigger of a trigger signal.

The extraction unit 3805 is configured to extract the identity information corresponding to the person in the video, and save the corresponding relationship between the identity information and the video.

It should be noted here that the above-mentioned first receiving unit 3801, first obtaining unit 3803, and extracting unit 3805 correspond to steps S102 to S106 in the first embodiment, and the above-mentioned units and corresponding steps implement the same examples and application scenarios. But it is not limited to the content disclosed in the first embodiment. It should be noted that, as a part of the device, the above-mentioned units can be executed in a computer system such as a set of computer-executable instructions.

It can be seen from the above that, in the above-mentioned embodiments of the present application, the first receiving unit can be used to receive the trigger signal, where the trigger signal is used to trigger the camera device to shoot, and the camera device includes a driving device and a camera, and the driving device is used to drive the camera device. The camera moves in the mobile; the camera is used for video shooting during the movement; then the first acquisition unit is used to acquire the video captured by the camera under the trigger of the trigger signal; then the extraction unit is used to extract the identity information corresponding to the person in the video , And save the corresponding relationship between the identity information and the video. Through the video processing device in this application, it is realized that the video containing the user and the identification information of the person recognized from the video are correspondingly saved in advance, and the user is obtained from the pre-stored video library according to the user's identification information. The purpose of the video is to achieve the technical effect of improving the reliability of the video processing method, improve the user experience, and then solve the technical problem of low reliability of the video processing method in the related technology.

In an optional embodiment, the video processing device further includes: a sensing unit configured to sense that someone is present in the shooting range of the camera device through a sensor provided on the camera device before receiving the trigger signal; The unit is used to send out a trigger signal in response to the sensing of the sensor.

In an optional embodiment, the sensor is at least one of the following: an infrared sensing unit, a radio frequency sensing unit, and a radar detection unit.

In an optional embodiment, the video processing device further includes: a second receiving unit, configured to receive a user's operation of a switch in the camera device before receiving the trigger signal; and a second response unit, configured to respond to Operate to issue a trigger signal.

In an optional embodiment, the switch is at least one of the following: a key switch unit, a touch switch unit, and a photoelectric switch unit.

In an optional embodiment, the video processing device further includes: a third receiving unit, configured to receive a user's operation on the software interface before receiving the trigger signal; and a third response unit, configured to respond to the operation, Send a trigger signal to the camera via the network.

In an optional embodiment, the device further includes: a third obtaining unit, configured to obtain the identification information of the camera device by scanning a graphical code set on the camera device before receiving the user's operation on the software interface; The display unit is used to display the operations that can be performed on the camera device on the software interface according to the identification information.

In an optional embodiment, the video processing apparatus further includes: a fourth obtaining unit, configured to obtain the information of the handheld device when the software interface displays the human handheld device before receiving the user's operation on the software interface Geographic location information; a display unit for displaying on the software interface the camera devices that can be controlled by a person within a predetermined range from the handheld device and the operations that can be performed on the camera device on the software interface according to the geographic location information.

Optionally, the video processing device further includes: a second acquiring unit, configured to extract the identity information corresponding to the person in the video from the video, and after storing the corresponding relationship between the identity information and the video, acquire the to-be-extracted The identification information of the video, and search for one or more videos corresponding to the identification information of the video to be extracted in the saved videos; the display unit is used to display one or more videos to the identification of the video to be extracted The user corresponding to the message.

In an optional embodiment, the extraction unit is used to identify the attachments and/or the biological characteristics of the person from the person; the characteristic information of the attachments and/or the characteristic information of the biological characteristics are used as the Identify the identity information of the person; the second acquisition unit is used to acquire the characteristic information of the attachments of the person and/or the identity information of the biological characteristics of the person, and the characteristic information of the attachments and/or the characteristic information corresponding to the biological characteristics Identification information determined as a person; wherein the attachment includes at least one of the following: clothing, accessories, and hand-held objects; the biological characteristics include at least one of the following: facial features, posture characteristics; the attachment is used to uniquely identify a person in a predetermined area.

Optionally, the extraction unit is also used to extract the sensed radio frequency identification information from the radio frequency signal; use the radio frequency identification information as the identity information for identifying the person; extract the identity mark that identifies the person from the network trigger signal Information; the second acquisition unit is also used to extract the sensed radio frequency identification information from the radio frequency signal, and determine the radio frequency identification information as the person's identity information; extract the person's identity information from the network trigger signal.

In an optional embodiment, when the number of people in the video is multiple, the extraction unit includes: a first recognition module, configured to recognize attachments and/or attachments on each person from the multiple people Or biological characteristics; the first storage module is used to determine the characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics as the identification information of each of the multiple persons, and the identification information of each of the multiple persons The corresponding relationship between a person's identification information and the video is saved.

In an optional embodiment, the first saving module includes: a first determining sub-module, configured to determine the time node at which the identification information of each of the multiple people is recognized in the video; and a second determining sub-module , Used to use the time node as the time label of the identification information of each of multiple people; save sub-module, used to identify the identification information of each of multiple people and the identification information of each of multiple people The corresponding relationship between the added time label and the video is saved.

In an optional embodiment, the movement trajectory of the camera includes at least one of the following: a reciprocating movement trajectory between a predetermined starting point and a predetermined end point, a cyclic movement trajectory of a predetermined path, a movement trajectory designed based on a predetermined programming program, and following the target The tracking movement trajectory of the object.

In an optional embodiment, the movement of the camera is at least one of the following: orbital movement and rotational movement.

In an optional embodiment, the driving mode of the driving device is at least one of the following: mechanical driving, electromagnetic driving, and pressure driving.

Example Nineteen

According to another aspect of the embodiments of the present application, a storage medium is also provided. The storage medium includes a stored program, wherein the program executes any one of the above-mentioned video processing methods.

Embodiment Twenty

According to another aspect of the embodiments of the present application, there is also provided a processor, which is configured to run a program, wherein the video processing method of any one of the above is executed when the program is running.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority or inferiority of the embodiments.

In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus. For a part that is not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units may be a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes. .

The above are only the preferred embodiments of this application. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and modifications can be made, and these improvements and modifications are also Should be regarded as the scope of protection of this application.

Claims

A video processing method, including:

A trigger signal is received, where the trigger signal is used to trigger a camera device to shoot, the camera device includes a drive device and a camera, the drive device is used to drive the camera in the camera device to move; the camera is used to Video shooting in the process of moving;

Acquiring a video captured by the camera under the trigger of the trigger signal;

Extract the identity information corresponding to the person in the video from the video, and save the corresponding relationship between the identity information and the video.
The method according to claim 1, wherein, before receiving the trigger signal, the method further comprises:

Sensing that someone appears in the shooting range of the camera device through a sensor provided on the camera device;

In response to the sensing of the sensor, the trigger signal is issued.
The method according to claim 2, wherein the sensor is at least one of the following: an infrared sensing unit, a radio frequency sensing unit, and a radar detection unit.
The method according to claim 1, wherein, before receiving the trigger signal, the method further comprises:

Receiving a user's operation on a switch in the camera device;

In response to the operation, the trigger signal is issued.
The method according to claim 4, wherein the switch is at least one of the following: a key switch unit, a touch switch unit, and a photoelectric switch unit.
The method according to claim 1, wherein, before receiving the trigger signal, the method further comprises:

Receive user operations on the software interface;

In response to the operation, the trigger signal is sent to the camera device via the network.
The method according to claim 4, wherein, before receiving a user's operation on the software interface, the method further comprises:

Acquiring the identification information of the camera device by scanning a graphical code set on the camera device;

The operations that can be performed on the camera device are displayed on the software interface according to the identification information.
The method according to claim 4, wherein, before receiving a user's operation on the software interface, the method further comprises:

In the case where the software interface displays the handheld device of the person, acquiring geographic location information of the handheld device;

According to the geographic location information, display on the software interface the camera devices that can be controlled by the person within a predetermined range from the handheld device and the operations that can be performed on the camera device.
The method according to claim 1, wherein after extracting the identification information corresponding to the person in the video from the video, and storing the corresponding relationship between the identification information and the video, The method also includes:

Obtain the identification information of the video to be extracted, and search for one or more videos corresponding to the identification information of the video to be extracted in the saved videos;

Displaying the one or more videos to the user corresponding to the identification information of the video to be extracted.
The method according to claim 9, wherein extracting the identification information corresponding to the person in the video from the video comprises: recognizing the attachment on the person from the person and/or the The biological characteristics of a person; the characteristic information of the attachment and/or the characteristic information of the biological characteristic are used as the identification information for identifying the person;

Obtaining the identification information of the video to be extracted includes: acquiring the characteristic information of the attachment of the person and/or the identification information of the biological characteristic of the person, and corresponding the characteristic information of the attachment and/or the biological characteristic The characteristic information of is determined as the identification information of the person; wherein, the attachment includes at least one of the following: clothing, accessories, and hand-held objects; the biological characteristics include at least one of the following: facial characteristics, body characteristics; The attachment is used to uniquely identify the person in the predetermined area.
The method according to claim 10, wherein extracting the identification information corresponding to the person in the video from the video comprises: extracting the sensed radio frequency identification information from the radio frequency signal; using the radio frequency identification information as The identification information used to identify the person; the identification information that identifies the person is extracted from the network trigger signal;

Obtaining the identification information of the video to be extracted includes: acquiring the radio frequency identification information sensed from the radio frequency signal, determining the radio frequency identification information as the identification information of the person; extracting the identification information from the network trigger signal The identification information of the person.
The method according to claim 11, wherein, in the case that the number of people in the video is multiple, extracting the identification information corresponding to the people in the video from the video comprises:

Identifying attachments and/or biological characteristics of each person from the plurality of persons;

Determine the characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics as the identification information of each of the plurality of persons, and identify the identity of each of the plurality of persons The corresponding relationship between the information and the video is saved.
The method according to claim 12, wherein storing the corresponding relationship between the identification information of each of the plurality of people and the video comprises:

Determine the time node at which the identification information of each of the plurality of people is recognized in the video;

Using the time node as a time label of the identification information of each of the plurality of people;

The identification information of each of the plurality of people and the corresponding relationship between the time stamp added to the identification information of each of the plurality of people and the video are stored.
The method according to claim 1, wherein the movement trajectory of the camera includes at least one of the following: a reciprocating movement trajectory between a predetermined starting point and a predetermined end point, a cyclic movement trajectory of a predetermined path, and a movement trajectory designed based on a predetermined programming program , Follow the tracking movement trajectory of the target object.
The method according to claim 14, wherein the movement of the camera is at least one of the following: orbital movement and rotational movement.
The method according to claim 1, wherein the driving mode of the driving device is at least one of the following: mechanical driving, electromagnetic driving, and pressure driving.
A video processing device includes:

The first receiving unit is configured to receive a trigger signal, wherein the trigger signal is used to trigger a camera device to take a picture, the camera device includes a driving device and a camera, and the driving device is used to drive the camera in the camera device Moving; the camera is used for video shooting during the moving process;

The first acquiring unit is configured to acquire a video captured by the camera under the trigger of the trigger signal;

The extraction unit is configured to extract the identity information corresponding to the person in the video from the video, and save the corresponding relationship between the identity information and the video.
The device according to claim 17, wherein the device further comprises:

The sensing unit is configured to sense that someone appears in the shooting range of the camera device through a sensor provided on the camera device before receiving the trigger signal;

The first response unit is configured to send out the trigger signal in response to the sensing of the sensor.
The device according to claim 18, wherein the sensor is at least one of the following: an infrared sensor unit, a radio frequency sensor unit, and a radar detection unit.
The device according to claim 17, wherein the device further comprises:

The second receiving unit is configured to receive a user's operation of the switch in the camera device before receiving the trigger signal;

The second response unit is configured to send out the trigger signal in response to the operation.
The device according to claim 20, wherein the switch is at least one of the following: a key switch unit, a touch switch unit, and a photoelectric switch unit.
The device according to claim 17, wherein the device further comprises:

The third receiving unit is configured to receive the user's operation on the software interface before receiving the trigger signal;

The third response unit is configured to send the trigger signal to the camera device via the network in response to the operation.
The device according to claim 20, wherein the device further comprises:

The third obtaining unit is configured to obtain the identification information of the camera device by scanning the graphical code set on the camera device before receiving the user's operation on the software interface;

The display unit is configured to display the operations that can be performed on the camera device on the software interface according to the identification information.
The device according to claim 20, wherein the device further comprises:

The fourth acquiring unit is configured to acquire geographic location information of the handheld device when the software interface displays the human handheld device before receiving the user's operation on the software interface;

A display unit configured to display on the software interface according to the geographic location information the camera device that can be controlled by the person within a predetermined range from the handheld device, and the operations that can be performed on the camera device .
The device according to claim 17, wherein the device further comprises:

The second acquiring unit is configured to, after extracting the identification information corresponding to the person in the video from the video, and saving the corresponding relationship between the identification information and the video, acquire the information of the video to be extracted Identification information, and search for one or more videos corresponding to the identification information of the video to be extracted in the saved videos;

The display unit is configured to display the one or more videos to the user corresponding to the identification information of the video to be extracted.
The device according to any one of claims 17 to 25, wherein the extraction unit is configured to identify the attachments on the person and/or the biological characteristics of the person from the person; The characteristic information of the attachment and/or the characteristic information of the biological characteristic as the identification information for identifying the person;

The second acquiring unit is configured to acquire the characteristic information of the attachment of the person and/or the identification information of the biological characteristic of the person, and compare the characteristic information of the attachment and/or the biological characteristic to the corresponding The characteristic information is determined as the identification information of the person; wherein, the attachment includes at least one of the following: clothing, accessories, and hand-held objects; the biological characteristic includes at least one of the following: facial characteristics, posture characteristics; the attachment The object is used to uniquely identify the person in a predetermined area.
The device according to claim 26, wherein the extraction unit is further configured to extract the sensed radio frequency identification information from the radio frequency signal; use the radio frequency identification information as the identification information for identifying the person; The identification information that identifies the person is extracted from the trigger signal;

The second acquisition unit is further configured to extract the sensed radio frequency identification information from the radio frequency signal, and determine the radio frequency identification information as the identification information of the person; and extract the identification information from the network trigger signal. The identification information of the person.
The device according to claim 27, wherein, in a case where the number of people in the video is multiple, the extracting unit comprises:

The first recognition module is configured to recognize attachments and/or biological characteristics of each person from among the plurality of persons;

The first storage module is configured to determine the characteristic information of the attachments on each person and/or the characteristic information corresponding to the biological characteristics as the identification information of each of the plurality of persons, and to determine the characteristic information of each of the plurality of persons The corresponding relationship between each individual's identification information and the video is stored.
The device according to claim 28, wherein the first storage module comprises:

The first determining submodule is configured to determine the time node at which the identification information of each of the plurality of people is recognized in the video;

The second determining sub-module is configured to use the time node as the time label of the identification information of each of the plurality of people;

The saving sub-module is configured to save the identification information of each of the plurality of people and the corresponding relationship between the time stamp added to the identification information of each of the plurality of people and the video.
The device according to claim 17, wherein the movement trajectory of the camera comprises at least one of the following: a reciprocating movement trajectory between a predetermined starting point and a predetermined end point, a cyclic movement trajectory of a predetermined path, and a movement trajectory designed based on a predetermined programming program , Follow the tracking movement trajectory of the target object.
The device according to claim 30, wherein the movement of the camera is at least one of the following: orbital movement and rotational movement.
The device according to claim 17, wherein the driving mode of the driving device is at least one of the following: mechanical driving, electromagnetic driving, and pressure driving.
A storage medium, characterized in that the storage medium includes a stored program, wherein the program executes the video processing method according to any one of claims 1 to 16.
A processor, characterized in that the processor is used to run a program, wherein the video processing method according to any one of claims 1 to 16 is executed when the program is running.